Vehicle parameter prediction method and device and computer equipment

Abstract

The invention discloses a vehicle parameter prediction method and device and computer equipment, and belongs to the vehicle-mounted field. The method comprises the steps of obtaining a dynamic model corresponding to a vehicle; the dynamic model obtains a state variable, a control variable and an output variable corresponding to the vehicle; based on the state variable, the control variable and the output variable, constructing a reference prediction model corresponding to the vehicle; acquiring a disturbance variable corresponding to the vehicle; based on the state variable, the control variable, the output variable and the disturbance variable, constructing a target prediction model corresponding to the vehicle; and constructing a vehicle parameter prediction model based on the difference between the reference prediction model and the target prediction model. And the controllability and comfort of vehicle control are improved.

Description

Technical Field

[0001] The present application relates to the vehicle field, and in particular to a method, device and computer equipment for predicting vehicle parameters. Background Art

[0002] As the level of vehicle intelligence continues to improve, the chassis control system in the vehicle includes active steering and active suspension. The vehicle chassis control system is used to ensure the control stability of the vehicle during the autonomous driving process.

[0003] In the related art, the chassis system in the vehicle is integrated with an active suspension controller, which determines the additional actuation force that the active suspension should add based on the vehicle's driving information to ensure that the vehicle body is in a stable state when dealing with different road conditions. For example, when the vehicle passes over a raised ground, the active suspension applies an additional upward actuation force to support the vehicle over the raised ground.

[0004] However, during the process of automatic driving of the vehicle, the external environment and road conditions that the vehicle has to deal with are uncontrollable. The active suspension controller focuses on the longitudinal movement of the vehicle. After the active suspension applies additional force, although it can ensure the controllability of the vehicle suspension, the sudden application of force to the suspension is unstable for the vehicle body. Summary of the invention

[0005] The present application provides a method, device and computer equipment for predicting vehicle parameters, while improving the controllability and comfort of vehicle control. The technical solution is as follows:

[0006] According to one aspect of the present application, a method for predicting vehicle parameters is provided, the method comprising:

[0007] Acquire a dynamic model corresponding to the vehicle, the dynamic model including a steering model, a suspension model and a tire model, and the dynamic model is used to construct a dynamic relationship between the driving state and the physical characteristics of the vehicle;

[0008] Based on the dynamic model, a state variable, a control variable and an output variable corresponding to the vehicle are obtained, wherein the state variable includes a first parameter related to the driving state and the physical characteristic, the control variable includes a second parameter related to the front wheel steering angle and the suspension force, and the output variable includes a yaw angle corresponding to the vehicle and a third parameter corresponding to the path displacement of the vehicle in the lateral direction;

[0009] Based on the state variable, the control variable and the output variable, construct a reference prediction model corresponding to the vehicle;

[0010] Acquiring a disturbance variable corresponding to the vehicle, wherein the disturbance variable is used to represent an environmental variable that generates a state disturbance on the driving state of the vehicle;

[0011] Based on the state variable, the control variable, the output variable and the disturbance variable, construct a target prediction model corresponding to the vehicle;

[0012] Based on the difference between the reference prediction model and the target prediction model, a vehicle parameter prediction model is constructed, wherein the vehicle parameter prediction model is used to predict the force of the vehicle suspension when the displacement of the vehicle changes.

[0013] According to one aspect of the present application, a vehicle parameter prediction device is provided, the device comprising:

[0014] An acquisition module, used to acquire a dynamic model corresponding to the vehicle, the dynamic model including a steering model, a suspension model and a tire model, and the dynamic model is used to construct a dynamic relationship between the driving state and the physical characteristics of the vehicle;

[0015] The acquisition module is further used to acquire state variables, control variables and output variables corresponding to the vehicle based on the dynamic model, wherein the state variables include first parameters related to the driving state and the physical characteristics, the control variables include second parameters related to the front wheel steering angle and the suspension force, and the output variables include a yaw angle corresponding to the vehicle and a third parameter corresponding to the path displacement of the vehicle in the lateral direction;

[0016] A construction module, used for constructing a reference prediction model corresponding to the vehicle based on the state variable, the control variable and the output variable;

[0017] The acquisition module is further used to acquire a disturbance variable corresponding to the vehicle, wherein the disturbance variable is used to represent an environmental variable that generates a state disturbance to the driving state of the vehicle;

[0018] The construction module is used to construct a target prediction model corresponding to the vehicle based on the state variable, the control variable, the output variable and the disturbance variable;

[0019] The construction module is used to construct a vehicle parameter prediction model based on the difference between the baseline prediction model and the target prediction model, and the vehicle parameter prediction model is used to predict the force of the vehicle suspension when the vehicle undergoes a displacement change.

[0020] According to one aspect of the present application, a computer device is provided, which includes a processor and a memory, wherein the memory stores a computer program, and the processor loads and executes the computer program to implement the above vehicle parameter prediction method.

[0021] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is loaded and executed by a processor to implement the above vehicle parameter prediction method.

[0022] According to another aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned vehicle parameter prediction method.

[0023] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0024] The steering system, suspension system and tire model corresponding to the vehicle are coupled to form a dynamic model. The variables corresponding to the front wheel steering angle and the path displacement in the lateral direction are introduced into the steering system to construct the corresponding benchmark prediction model of the vehicle. Then, the road excitation conditions of the vehicle during actual driving are simulated to generate disturbance variables. The target prediction model is generated based on the disturbance variables and the three variables corresponding to the dynamic model (state variables, output variables and control variables). Then, based on the difference between the target prediction model and the benchmark prediction model, a vehicle parameter prediction model is constructed. In actual application, the vehicle parameter prediction model is built into the intelligent driving system in the vehicle. During the driving process of the vehicle, the corresponding suspension force when the vehicle displacement changes is predicted based on information such as the vehicle speed, and the corresponding suspension is called to apply the corresponding force. Further improve the operational stability of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 is a schematic diagram of a method for predicting vehicle parameters provided by an exemplary embodiment of the present application;

[0027] Figure 2 is a flowchart of a method for predicting vehicle parameters provided by an exemplary embodiment of the present application;

[0028] Figure 3 is a schematic diagram of a steering model provided by an exemplary embodiment of the present application;

[0029] Figure 4 is a schematic diagram corresponding to a side view of a suspension model provided by an exemplary embodiment of the present application;

[0030] Figure 5 is a schematic diagram corresponding to a front view of a suspension model provided by an exemplary embodiment of the present application;

[0031] Figure 6 is a flowchart of a method for predicting vehicle parameters provided by another exemplary embodiment of the present application;

[0032] Figure 7 is a flowchart of a method for predicting vehicle parameters provided by yet another exemplary embodiment of the present application;

[0033] Figure 8 is a flowchart of a vehicle parameter prediction device provided by an exemplary embodiment of the present application;

[0034] Fig. 9 is a flowchart of a vehicle parameter prediction device provided by another exemplary embodiment of the present application;

[0035] Fig.10 is a structural block diagram corresponding to a computer device provided by an exemplary embodiment of the present application;

[0036] Fig.11 It is a structural block diagram corresponding to a server provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0037] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0038] The vehicle parameter prediction method provided in the embodiments of the present application can be implemented by the vehicle alone, by the server alone, or by the server and the vehicle together.

[0039] When the method is implemented by a vehicle alone, the model / calculation program related to the vehicle parameter prediction method is integrated into the vehicle's intelligent driving system, and during the vehicle's automatic driving process, the above-mentioned vehicle parameter prediction method is implemented through the intelligent driving system.

[0040] This paper takes the method implemented by the server and the vehicle as an example. Figure 1 The following is a block diagram of an execution structure of a method for predicting vehicle parameters provided by an exemplary embodiment, and the method is applied to the server 100 as an example for illustration.

[0041] Optionally, the server 100 obtains physical characteristics corresponding to the vehicle in the driving state, and the physical characteristics are used to characterize the driving parameters of the vehicle during driving (such as driving acceleration, etc.), tire parameters corresponding to the vehicle tires (such as steering angles corresponding to the four tires, etc.) and suspension parameters corresponding to the vehicle suspension (such as stiffness corresponding to the active suspension in the vehicle, etc.).

[0042] The server 100 generates a dynamic model corresponding to the vehicle based on the physical characteristics, and the dynamic model is used to construct a dynamic relationship between the driving state of the vehicle and the physical characteristics, so that relevant personnel can more intuitively understand the parameters corresponding to the steering, active suspension and tires of the vehicle.

[0043] The server 100 divides all physical characteristics into state variables, control variables and output variables based on the dynamic model.

[0044] The server 100 constructs a reference prediction model 101 corresponding to the vehicle based on the state variables, the control variables, and the output variables.

[0045] The server 100 receives the disturbance variables, and constructs a target prediction model 102 corresponding to the vehicle in combination with the state variables, the control variables and the output variables.

[0046] The server 100 constructs a vehicle parameter prediction model 103 based on the difference between the reference prediction model 101 and the target prediction model 102 .

[0047] In the process of applying the vehicle prediction model 103, the server 100 receives the physical characteristics to be predicted related to the control variables during the driving process of the vehicle, and inputs the physical characteristics to be predicted into the vehicle parameter prediction model 103. The vehicle parameter prediction model 103 realizes functions such as vehicle path tracking and suspension force prediction.

[0048] In the above process, only the execution process of the server 100 is introduced. In actual application, the server 100 can perform the above data interaction with the terminal or with the vehicle, and this application does not limit this. The terminal is any intelligent device with data interaction capability.

[0049] It is worth noting that when the terminal 10 is implemented as an intelligent terminal, the intelligent terminal can be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4), a laptop computer or a desktop computer. The terminal can also be called a user device, a portable terminal, a laptop terminal, a desktop terminal or other names, which are not limited in this application.

[0050] The server 100 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Optionally, the server 100 can also be implemented as a node in a blockchain system.

[0051] In the embodiment of the present application, the vehicle parameter prediction model 103 is integrated into the intelligent driving system in the vehicle. When the vehicle is in a driving state, the intelligent driving system in the vehicle directly obtains the physical features to be predicted generated during the driving process, inputs the physical features to be predicted into the vehicle prediction model 103, and outputs the path tracking results and suspension forces.

[0052] It should be noted that the information (including but not limited to vehicle information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0053] like Figure 2 As shown, Figure 2 The flowchart of the execution of the vehicle parameter prediction method provided by an exemplary embodiment of the present application is shown, and the execution subject of the method is a server as an example for explanation.

[0054] Step 201, obtaining a dynamic model corresponding to the vehicle.

[0055] Among them, the dynamic model is used to construct the dynamic relationship between the vehicle's driving state and physical characteristics.

[0056] During the driving process of the vehicle, the intelligent driving system in the vehicle obtains the physical characteristics corresponding to the vehicle. The physical characteristics are used to characterize the driving parameters of the vehicle during the driving process, the tire parameters corresponding to the vehicle tires, and the suspension parameters corresponding to the vehicle suspension.

[0057] The driving parameters include but are not limited to at least one of the lateral speed, longitudinal speed, yaw angle, yaw angular velocity, acceleration, lateral displacement, longitudinal displacement, etc. of the vehicle during driving.

[0058] The tire parameters are used to indicate the force parameters corresponding to the tires of the vehicle body. The tire parameters include but are not limited to the corresponding cornering force at the tires of the vehicle body.

[0059] The suspension parameters are used to indicate the parameters of the elastic elements in the suspension system of the vehicle in the lateral direction (direction pointing to the left of the vehicle's center of mass), longitudinal direction (direction pointing to the front of the vehicle's center of mass), and vertical direction (vertical to the vehicle's center of mass). The suspension parameters include but are not limited to at least one of the body roll moment of inertia, pitch moment of inertia, vertical moment of inertia, etc.

[0060] In the embodiment of the present application, the dynamic model includes a steering model, a suspension model and a tire model.

[0061] The steering model is established by referring to the following physical characteristics, which include vehicle mass m, sprung mass (the sum of the mass supported by the elastic elements in the vehicle suspension system) m s , vehicle longitudinal speed v x , vehicle lateral speed v y , yaw rate (the speed at which the vehicle rotates around the vertical direction during rotation) ω, cornering force corresponding to the four tires (the lateral reaction force acting on the tires by the ground) S i (where i = 1, 2, 3, 4), the height of the center of mass from the ground h, the front wheel turning angle (referring to the maximum angle that the front wheel can reach when turning) δ f , the vehicle's yaw moment of inertia (the moment of inertia of the vehicle when it rotates around the vertical axis) z , the distance from the center of mass to the front wheel a, the distance from the center of mass to the rear wheel b, the body roll angle (refers to the inclination angle of the vehicle body relative to the vertical direction when the vehicle is turning or driving on an uneven road) φ, the yaw angle (refers to the difference between the vehicle heading angle and the sideslip angle of the center of mass) The longitudinal position Y and lateral position X of the vehicle in the vehicle global coordinate system, the longitudinal cornering stiffness of the front tire of the vehicle (referring to the stiffness characteristics of the tire during longitudinal slip) C lf 、Longitudinal cornering stiffness of the vehicle's rear tires C lr , the slip rate of the front wheel (refers to the proportion of the sliding component of the tire during movement) S f and the rear wheel slip rate S r .

[0062] In the embodiment of the present application, the steering model can refer to the following formulas 1 to 5.

[0063] Formula 1:

[0064] Formula 2:

[0065] Formula 3:

[0066] Formula 4:

[0067] Formula 5:

[0068] The meanings of the parameters in the above formulas 1-5 can be found in the above content. Refers to the lateral vehicle speed v y Find the first-order derivative, It refers to the longitudinal speed v x Find the first-order derivative, It refers to the second-order derivative of the body roll angle. It refers to the first-order derivative of the yaw angular velocity ω, It refers to the first-order derivative of the longitudinal position Y. It refers to the first-order derivative of the lateral position X.

[0069] The following physical characteristics are used to construct the suspension model. The physical characteristics include the body roll moment of inertia (the moment of inertia of the vehicle when it rotates around the lateral direction) x , pitch moment of inertia (refers to the moment of inertia of the vehicle when it rotates around the longitudinal axis I y , the total force F acting on the vehicle body by the suspension at each wheel i (where i = 1, 2, 3, 4), constant d, vertical displacement z at the center of mass of the vehicle s , gravitational acceleration g and vehicle body pitch angle θ (referring to the height difference between the front position and the rear position of the vehicle). In the embodiment of the present application, d is half of the wheelbase.

[0070] In an embodiment of the present application, the suspension model includes the pitch motion equation corresponding to the sprung mass, the roll motion equation corresponding to the sprung mass, the vertical motion equation corresponding to the sprung mass, the vertical motion equation of the non-suspension mass, the force equation of the suspension on the vehicle body, and the displacement corresponding to the four tires of the vehicle body.

[0071] The pitch motion equation can be found in the following formula 6, the roll motion equation can be found in the following formula 7, and the vertical motion equation can be found in the following formula 8.

[0072] Formula 6:

[0073] Formula 7:

[0074] Formula 8:

[0075] In the above formulas 6-8, the parameters are marked with dots and double dots, which respectively represent the first-order derivative and the second-order derivative of the parameters.

[0076] The vertical motion equation of the non-suspended mass can be expressed as the following formula 9.

[0077] Formula 9:

[0078] In the above formula 9, m ui is the mass portion corresponding to the four elastic elements of the vehicle (i = 1, 2, 3, 4), k t Refers to the vertical stiffness of the four tires, z gi Refers to the vertical displacement of the road surface (i=1,2,3,4), z ui Refers to the vertical displacement corresponding to the four elastic elements of the vehicle.

[0079] Based on the above formula, combined with the damping coefficients c corresponding to the four suspensions i (i=1, 2, 3, 4), the suspension stiffness k corresponding to the four suspensions si (i=1, 2, 3, 4), front suspension lateral stabilizer bar angular stiffness k af , angular stiffness of rear suspension lateral stabilizer bar k ar and the vertical displacement z of the connection between the four suspensions and the vehicle body si (i=1, 2, 3, 4) determine F i The force equation can be found in the following formulas 10-13.

[0080] Formula 10:

[0081] Formula 11:

[0082] Formula 12:

[0083] Formula 13:

[0084] The parameters in the above formulas 11-13 can be found in the above text description.

[0085] In the embodiment of the present application, when the pitch angle θ has similar values ​​within the preset range, the vertical displacement z at the center of mass of the vehicle can be directly used. s, pitch angle θ, distance a from the center of mass to the front wheel, distance b from the center of mass to the rear wheel, and body roll angle φ directly determine the vertical displacement z of the connection between the four suspensions and the body si For details, please refer to the following formulas 14-17.

[0086] Formula 14: z s1 =z s -aθ-dφ;

[0087] Formula 15: z s2 =z s -aθ+dφ;

[0088] Formula 16: z s3 =z s +bθ+d;

[0089] Formula 17: z s4 =z s +bθ-dφ;

[0090] The parameters in the above formulas 14-17 can be found in the above text description.

[0091] The tire model is constructed by taking into account the following physical characteristics. Optionally, the cornering forces S corresponding to the four tires are i (where i = 1, 2, 3, 4) is used to characterize the tire model. For details, please refer to the following formulas 18-19.

[0092] Formula 18:

[0093] Formula 19:

[0094] In formula 18-19, k 1 , k 2 are the cornering stiffness of the front and rear wheels, α 1 , α 2 They are the sideslip angles of the front and rear wheels respectively. For other parameters, please refer to the above content.

[0095] Combining the above three models and Figure 3 , establish a vehicle steering model corresponding to the vehicle 300 in the vehicle global coordinate system. The vehicle steering model includes a vehicle coordinate system, the vehicle coordinate system takes the center of mass of the vehicle 300 as the origin, the x-axis pointing to the front of the vehicle 300, and the y-axis pointing to the left of the vehicle 300. The vehicle 300 includes tires 1-4, and the corresponding parameters of the vehicle 300 under the specified steering trajectory 301 are shown in the figure. The parameters can be found in the above text description content, which will not be repeated here.

[0096] like Figure 4 As shown, Figure 4A side view of a vehicle suspension model 400 corresponding to the vehicle is shown. The various parameters appearing in the vehicle suspension model 400 are also referred to the above text content and will not be repeated here.

[0097] like Figure 5 As shown, Figure 5 A front view of a vehicle suspension model 500 corresponding to the vehicle is shown. The various parameters appearing in the vehicle suspension model 500 are also referred to the above text content and will not be repeated here.

[0098] Step 202: Acquire state variables, control variables, and output variables corresponding to the vehicle based on the dynamics model.

[0099] Optionally, based on the above content, the physical characteristics included in the dynamic model are divided to obtain state variables, control variables and output variables.

[0100] Among them, the state variables include a first parameter related to the driving state and the physical characteristics, the control variables include a second parameter related to the front wheel steering angle and the suspension force, and the output variables include a yaw angle corresponding to the vehicle and a third parameter corresponding to the path displacement of the vehicle in the lateral direction.

[0101] Optionally, the first parameter (state variable) includes v y 、v x ,ω,X,θ, z s , Y, φ, z ui , At least one of . Wherein, i takes the value of 1, 2, 3, or 4.

[0102] In the embodiment of the present application, the first parameter (state variable) includes the above x y 、v x ,ω,X,θ, z s , Y, φ, z ui as well as

[0103] The second parameter (control variable) includes the front wheel steering angle and the corresponding actuation forces of the four suspension actuators, that is, the second parameter includes δ and f i At least one of . Wherein, i takes the value of 1, 2, 3, or 4.

[0104] In the embodiment of the present application, the second parameter (control variable) includes δ and f i Five parameters.

[0105] The third parameter (output variable) includes Y. θ、φ、z s1 -z u1 、z s2 -z u2 、z s3 -z u3 、z s4 -z u4 at least one of .

[0106] In the embodiment of the present application, the third parameter (output variable) includes Y. θ、φ、z s1 -z u1 、z s2 -z u2 、z s3 -z u3 and z s4 -z u4 .

[0107] Step 203: construct a reference prediction model corresponding to the vehicle based on the state variables, control variables and output variables.

[0108] Optionally, an initial prediction model is obtained, and input features corresponding to the state variables, control variables, and output variables are input into the initial prediction model to obtain a first candidate prediction result. The first candidate prediction result is compared with a theoretical prediction result corresponding to the input features to obtain a difference parameter; the initial prediction model is adjusted based on the difference parameter to obtain a benchmark prediction model.

[0109] In another optional embodiment, a nominal equation corresponding to the vehicle is determined based on the state variables, the control variables and the output variables, and a reference prediction model is constructed according to the nominal equation, wherein the nominal equation is used to represent the corresponding relationship between the state variables, the control variables and the output variables.

[0110] Schematically, the nominal equations can be found in the following formulas 20-21.

[0111] Formula 20: x new =Ax+Bu;

[0112] Formula 21: y = Cx + Du;

[0113] In the above formulas 20-21, x new represents the first parameter, u represents the second parameter, y represents the third parameter, and A, B, C, and D are matrices of preset dimensions respectively.

[0114] A benchmark prediction model is constructed based on the above nominal equation.

[0115] The above nominal equation is linearized to obtain a linear nominal equation. Specifically, the above nominal equation is linearized and solved based on the dimension n of the state variable and the dimension m of the output variable. The specific linearization solution process can be found in the following formula 22.

[0116] Formula 22:

[0117] In the above formula 22, It refers to the derivation of the wallpaper of the first variable in the output variable and the first variable in the state variable. The remaining ratios in formula 22 are consistent with the solution method of this ratio.

[0118] Optionally, determine the objective function corresponding to the control variable and the output variable. The objective function is used to characterize the corresponding relationship of the longitudinal position Y under the influence of the control variable.

[0119] Specifically, the ideal path displacement corresponding to the vehicle is determined based on the initial state model; and the objective function is determined based on the ideal path displacement and the control variable.

[0120] Schematically, the objective function is based on the actual longitudinal position Y of the vehicle, the ideal longitudinal position And the control variables are determined.

[0121] In the embodiment of the present application, Y and For all parameters in the above output variables.

[0122] In an optional embodiment, a discretization process is performed on the linear nominal equation to obtain a discrete state equation; a rolling prediction process is performed on the discrete state equation to obtain a rolling state equation; and an objective function is determined based on the rolling state equation. The discretization process here refers to using the current state variables and output variables to determine the state variables and control variables corresponding to the vehicle at the next moment. The rolling prediction process refers to continuously updating the prediction results as new physical features continue to appear.

[0123] Schematically, the above formulas 20-21 are discretized to obtain the following formulas 23-24, which are discrete state equations.

[0124] Formula 23: x(k+1)=A k x(k)+B k u(k);

[0125] Formula 24: y(k) = C k x(k)+D k u(k);

[0126] In the above formulas 23-24, k is an integer greater than 0. When k takes different values, the parameters A, B, C, and D in formulas 23-24 are also different. k can also be understood as the number of iterations of the state variables, control variables, and output variables during the discretization process.

[0127] In an optional embodiment, after obtaining the discretized equation, the conversion control variable generates the conversion control variable. Schematically, the expression corresponding to the conversion control variable is ξ(k|t)=[x(k)u(k-1)] T , where k is the number of iterations, t is the current time, and T refers to the transpose operation.

[0128] The conversion nominal equation is generated based on the conversion control variable. The conversion nominal equation can be seen in the following formulas 25-26.

[0129] Formula 25:

[0130] Formula 26:

[0131] In the above formulas 25-26, Δu(k)=[Δδf 1 f 2 f 3 f 4 ], Δδ refers to the change in the front wheel angle within the target time period. Used to represent the matrix values ​​corresponding to the above matrices A, B, and C during the kth iteration.

[0132] The rolling prediction is performed on the discrete state equation corresponding to Formula 20-21 to obtain the rolling state equation. For details, please refer to the following Formula 27.

[0133] Formula 27:

[0134] In the above formula 27:

[0135] Np is the prediction time domain, and Nc is the control time domain.

[0136] Determine the objective function. Specifically, determine the ideal path displacement corresponding to the vehicle based on the initial state model; determine the objective function based on the ideal path displacement and the control variables.

[0137] In an optional embodiment, the actual longitudinal position Y and the ideal longitudinal position Y corresponding to the vehicle are obtained. and control variables, and generate an objective function based on these three parameters. The objective function can be found in the following formula 28, where the parameters appearing in formula 28 all appear in the above text content and are not repeated here.

[0138] Formula 28:

[0139] In the above formula 28, Q Q is the weight of the output variable, R R is the weight of the control variable.

[0140] Optionally, a minimum value corresponding to the control variable in the objective function is determined; based on the minimum value and the linear nominal equation, the initial prediction model is adjusted to obtain a benchmark prediction model.

[0141] The process of determining the minimum value is as follows: determining the constraint condition corresponding to the front wheel steering angle, which is used to indicate the value range corresponding to the front wheel steering angle; based on the constraint condition, using a preset solution method to determine the minimum value corresponding to the control variable in the objective function. The preset solution method is a quadratic programming solution method.

[0142] In the embodiment of the present application, the front wheel steering angle and the actuating force in the control variables are constrained, that is, the constraint conditions corresponding to the front wheel steering angle and the actuating force are determined, and the constraint conditions are determined by the relevant personnel according to the actual situation of the vehicle.

[0143] In the embodiment of the present application, the constraint conditions include the value range corresponding to the front wheel steering angle and the value range of the actuating force. f The range is [-3.5rad≤δ f ≤3.5rad], front wheel steering angle change Δδ f The range is [-0.35rad≤Δδ f ≤3.5rad]. The range of the operating force f is [-5000N≤f≤5000N].

[0144] The minimum value corresponding to the control variable increment is determined using the following formula 29.

[0145] Formula 29:

[0146] In the above formula 29, The control variable and the control variable increment conform to a preset relationship u(k+o)=u(k+o-1)+Δu(k), where o is an integer greater than 0.

[0147] Optionally, the minimum value corresponding to the control variable increment is determined using a quadratic programming solution method. Schematically, the QP solver quadprog provided by the matrix factory (ie, Matlab software) is used to solve the objective function to obtain the minimum value.

[0148] Based on the minimum value and the rolling state equation, the initial prediction model is adjusted to obtain a benchmark prediction model.

[0149] Step 204: Obtain the disturbance variable corresponding to the vehicle.

[0150] Optionally, the disturbance variable is used to represent the environmental variable that generates state disturbance to the driving state of the vehicle. The disturbance variable can be regarded as the road surface excitation during the driving process of the vehicle. The road surface excitation refers to the dynamic excitation of the vehicle caused by the unevenness of the road surface during the driving process of the vehicle, which affects the vibration, comfort, safety and corresponding dynamic performance of the vehicle.

[0151] In the embodiment of the present application, the road surface excitation (disturbance variable) is composed of random unevenness and discrete events. Random unevenness refers to the uneven section corresponding to the road surface, and the discrete events are caused by circular protrusions, arched protrusions, and corrugated road surfaces.

[0152] In another optional embodiment, the disturbance variable also includes sub-variables representing environmental information such as wind parameters, temperature parameters, and humidity parameters.

[0153] Based on the above, it can be seen that the disturbance variables include variables corresponding to random unevenness, variables corresponding to discrete events, and sub-variables.

[0154] Step 205, constructing a target prediction model corresponding to the vehicle based on the state variables, control variables, output variables and disturbance variables.

[0155] Optionally, an initial prediction model is obtained. Input features corresponding to disturbance variables, state variables, control variables, and output variables are input into the initial prediction model to obtain candidate prediction results. The candidate prediction results are compared with theoretical prediction results corresponding to the input features to obtain difference parameters; the initial prediction model is adjusted based on the difference parameters to obtain a target prediction model.

[0156] Step 206 , constructing a vehicle parameter prediction model based on the difference between the baseline prediction model and the target prediction model.

[0157] Optionally, the data to be predicted is obtained, and the data to be predicted is simultaneously input into the reference prediction model and the target prediction model to obtain a first result corresponding to the reference prediction model and a second result corresponding to the target prediction model. The first result and the second result are fitted to obtain a third result.

[0158] The third result is used as an input to the target prediction model to obtain a fourth result. Based on the difference between the third result and the fourth result, the model parameters in the target prediction model are corrected to obtain a vehicle parameter prediction model.

[0159] In another optional embodiment, the above-mentioned reference prediction model and target prediction model are coupled to obtain a vehicle parameter prediction model, wherein the coupling process includes establishing a coupling initial model, determining an excitation input, simulation analysis, parameter impact analysis, and verification optimization process.

[0160] Among them, establishing the coupling initial model means establishing the dynamic model corresponding to the vehicle and the road surface dynamic model under the condition of coupling between the vehicle and the road surface, and determining the interaction between the two models. Schematically, the vehicle and the road are connected through the displacement compatibility condition at the contact point between the tire and the road surface, so as to establish the coupling initial model corresponding to the vehicle-road coupling system.

[0161] Determining the excitation input means taking the road surface excitation as the input of the vehicle response in the coupled initial model to simulate the road surface roughness. Usually, a Gaussian stationary random process is used to simulate the road surface roughness and generate an unequal degree sequence at different road surface roughness levels, which is presented in the form of a matrix.

[0162] Simulation analysis refers to the use of simulation tools to simulate the coupled initial model. During the simulation process, the inequality sequence corresponding to the road surface excitation is used as input to analyze the vehicle's response to the road surface excitation.

[0163] Parameter impact analysis refers to analyzing the impact of different physical characteristics on the coupled initial system, including the impact of vehicle speed changes, the impact of road inequality changes on vehicle dynamic load coefficients and vehicle vertical acceleration, and the impact of different road base stiffness on vehicle vibration characteristics.

[0164] The verification and optimization process refers to verifying the accuracy and reliability of the coupling initial model through experiments and actual tests. According to the verification results, the coupling initial model is optimized to obtain the above-mentioned vehicle parameter prediction model.

[0165] Among them, the vehicle parameter prediction model is used to realize path tracking and predict suspension force and other functions.

[0166] Among them, path tracking refers to the displacement information of the vehicle under the current driving state corresponding to the future moment, and the predicted suspension force refers to the prediction of the pressure exerted by the four suspensions of the vehicle when facing the road conditions at the future moment.

[0167] In schematic form, the current speed of the vehicle and the road inequality level are input into the vehicle parameter prediction model to predict a series of physical characteristics of the vehicle, such as the lateral position, longitudinal position, yaw angle, pitch angle, and roll angle at a future moment. Based on the prediction results corresponding to the physical parameters related to the suspension, the suspension is driven to apply additional force to ensure the ride comfort of the vehicle in various road conditions during driving. On the other hand, the vehicle parameter prediction model is used to predict the corresponding active front wheel steering angle of the vehicle to ensure the ability to track the vehicle's driving path.

[0168] In an embodiment of the present application, the steering system, suspension system and tire model corresponding to the vehicle are coupled to form a dynamic model, and the variables corresponding to the front wheel angle and the path displacement in the lateral direction are introduced into the steering system to construct a reference prediction model corresponding to the vehicle. Then, the road surface excitation conditions of the vehicle during actual driving are simulated to generate disturbance variables. A target prediction model is generated based on the disturbance variables and the three variables (state variables, output variables and control variables) corresponding to the dynamic model. Then, based on the difference between the target prediction model and the reference prediction model, a vehicle parameter prediction model is constructed. In actual application, the vehicle parameter prediction model is built into the intelligent driving system in the vehicle. During the driving process of the vehicle, the corresponding suspension actuating force when the vehicle displacement changes is predicted based on information such as the vehicle speed, and the corresponding suspension is called to apply the corresponding actuating force. Further improve the operational stability of the vehicle.

[0169] like Figure 6 As shown, Figure 6 The flowchart of the method for predicting vehicle parameters provided by another exemplary embodiment of the present application is shown, and the method is described with the execution subject being a server.

[0170] Step 600, constructing a vehicle parameter prediction model.

[0171] Obtain the nominal equation and disturbance variables corresponding to the vehicle. Adjust the nominal equation based on the disturbance variables to determine the actual state equation corresponding to the vehicle.

[0172] Optionally, the disturbance variable is denoted by w(k).

[0173] Formulas 23-24 are adjusted based on the disturbance variable w(k) to obtain the following formulas 31-32, which are used to represent the actual nominal equations generated by the vehicle driving during actual application.

[0174] Formula 31:

[0175] Formula 32:

[0176] In the above formulas 31-32, They are the state vector, control vector and output vector corresponding to the vehicle in actual application, and w(k) is the disturbance input.

[0177] In another optional embodiment, the error state equation is determined based on the nominal equation and the actual state equation. That is, the error state equation is obtained by subtracting the nominal state equation obtained in the above process from the actual nominal equation. in,

[0178] Optionally, based on the above error state equation, a vehicle parameter prediction model is obtained.

[0179] Optionally, determine an error prediction model corresponding to the error state equation; couple the error prediction model and the benchmark prediction model to obtain a vehicle parameter prediction model.

[0180] In another optional embodiment, a linear quadratic regulator (LQR for short) is used to solve the minimum value corresponding to each variable in the error nominal state system.

[0181] The LQR controller is explained below.

[0182] The core of the LQR controller is to minimize the target quadratic cost function, which can be expressed as follows:

[0183] Formula 33:

[0184] in, represents the nominal system model performance output cost, and Q is the performance weighting matrix. represents the vehicle controller cost and R is the control weighting matrix. represents the terminal cost, S is the vehicle weighting matrix, I and N are positive integers, Used to represent the mean corresponding to the I-th output variable.

[0185] Determine the feedback gain matrix of the LQR controller. The feedback gain matrix can be determined by referring to the following formula 34.

[0186] Formula 34:

[0187] In the above formula 34, N is a positive integer, q is any value between 1 and N, and P is a solution of the Laplace-Markov equation.

[0188] Based on the above objective function, an LQR controller is designed. In the embodiment of the present application, the controller is Where K is the feedback gain matrix of the LQR controller.

[0189] Based on the state variables and output variables, combined with the feedback gain matrix K, an LQR controller is generated.

[0190] The model corresponding to the above LQR controller and the benchmark prediction model are coupled to generate a vehicle parameter prediction model.

[0191] In another optional embodiment, a preset algorithm (here referring to the LRQ control algorithm) is used to solve the minimum value corresponding to each output variable under the error nominal state system; the error prediction model is trained based on the minimum value to obtain a target error prediction model; the target error prediction model and the benchmark prediction model are coupled to obtain a vehicle parameter prediction model.

[0192] In an embodiment of the present application, the steering system, suspension system and tire model corresponding to the vehicle are coupled to form a dynamic model, and the variables corresponding to the front wheel angle and the path displacement in the lateral direction are introduced into the steering system to construct a reference prediction model corresponding to the vehicle. Then, the road surface excitation conditions of the vehicle during actual driving are simulated to generate disturbance variables. A target prediction model is generated based on the disturbance variables and the three variables (state variables, output variables and control variables) corresponding to the dynamic model. Then, based on the difference between the target prediction model and the reference prediction model, a vehicle parameter prediction model is constructed. In actual application, the vehicle parameter prediction model is built into the intelligent driving system in the vehicle. During the driving process of the vehicle, the corresponding suspension actuating force when the vehicle displacement changes is predicted based on information such as the vehicle speed, and the corresponding suspension is called to apply the corresponding actuating force. Further improve the operational stability of the vehicle.

[0193] like Figure 7 As shown, Figure 7 The flowchart of the method for predicting vehicle parameters provided by another exemplary embodiment of the present application is shown, and the method is described with the execution subject being a server.

[0194] Step 700, constructing a dynamic model.

[0195] Optionally, a steering model, a suspension model, and a tire model of the vehicle chassis are established.

[0196] For the specific execution process of this step, please refer to the above step 201, which will not be repeated here.

[0197] Step 701 : coupling the dynamics model and performing linearization processing on the coupled dynamics model.

[0198] Optionally, the three models are coupled and the coupled models are linearized by the Jacobian matrix. This process includes determining variables related to the nominal equation and linearizing the related variables.

[0199] Optionally, the state variables, control variables and output variables are determined based on the dynamic model, and the above three variables are transformed into nominal equations for linearization through the Jacobian matrix method.

[0200] For the specific execution process of this step, please refer to the above steps 201-202, which will not be repeated here.

[0201] Step 702 , design a model predictive controller for the nominal system.

[0202] Optionally, a nominal equation is determined based on the state variables, the control variables and the output variables. The nominal equation is discretized and a rolling forecast is performed, and then a suitable objective function and constraint conditions are selected to optimize and solve the control quantity of the nominal equation.

[0203] The initial prediction model is adjusted 203 using the solved control variable to obtain a model predictive controller.

[0204] For the specific implementation process of this step, please refer to the above steps and will not be repeated here.

[0205] Step 703: construct an error system and design a target controller for the error system.

[0206] Optionally, a disturbance variable is introduced to design an actual nominal equation, the error system is obtained by subtracting the nominal equation from the actual nominal equation, and an LQR controller is designed for the error system using an LQR controller.

[0207] For the specific execution process of this step, please refer to the above step 206, which will not be repeated here.

[0208] Step 704 , coupling the model predictive controller and the LQR controller to generate a pipeline model predictive controller.

[0209] Optionally, couple the two designed controllers to create a pipeline model predictive controller.

[0210] For the specific execution process of this step, please refer to the above step 600, which will not be repeated here.

[0211] In an embodiment of the present application, the steering system, suspension system and tire model corresponding to the vehicle are coupled to form a dynamic model, and the variables corresponding to the front wheel angle and the path displacement in the lateral direction are introduced into the steering system to construct a reference prediction model corresponding to the vehicle. Then, the road surface excitation conditions of the vehicle during actual driving are simulated to generate disturbance variables. A target prediction model is generated based on the disturbance variables and the three variables (state variables, output variables and control variables) corresponding to the dynamic model. Then, based on the difference between the target prediction model and the reference prediction model, a vehicle parameter prediction model is constructed. In actual application, the vehicle parameter prediction model is built into the intelligent driving system in the vehicle. During the driving process of the vehicle, the corresponding suspension actuating force when the vehicle displacement changes is predicted based on information such as the vehicle speed, and the corresponding suspension is called to apply the corresponding actuating force. Further improve the operational stability of the vehicle.

[0212] In an optional embodiment, the vehicle parameter prediction method provided above is integrated into an intelligent driving system and presented in the form of a chassis prediction controller. During the automatic driving process of the vehicle, the chassis prediction controller obtains the physical characteristics and road excitations corresponding to the vehicle, controls the steering system corresponding to the vehicle, and predicts the additional force applied by the suspension system to achieve robust control of the vehicle chassis. The front wheel angle is output for the active steering system to achieve path tracking control and vehicle stability control. For the active suspension system, the suspension force output by the chassis prediction controller can achieve vehicle ride comfort control. The chassis prediction controller has high robustness, so that when the vehicle faces disturbances in the external environment (such as side wind, road excitation, slippery road surface, etc.), the chassis prediction controller can still achieve vehicle stability control.

[0213] Figure 8 The structure block diagram of a vehicle parameter prediction device provided by an exemplary embodiment of the present application is shown, and the device includes:

[0214] An acquisition module 800 is used to acquire a dynamic model corresponding to the vehicle, wherein the dynamic model includes a steering model, a suspension model and a tire model, and the dynamic model is used to construct a dynamic relationship between the driving state and the physical characteristics of the vehicle;

[0215] The acquisition module 800 is further used to acquire state variables, control variables and output variables corresponding to the vehicle based on the dynamic model, wherein the state variables include first parameters related to the driving state and the physical characteristics, the control variables include second parameters related to the front wheel steering angle and the suspension force, and the output variables include a yaw angle corresponding to the vehicle and a third parameter corresponding to the path displacement of the vehicle in the lateral direction;

[0216] A construction module 801 is used to construct a reference prediction model corresponding to the vehicle based on the state variable, the control variable and the output variable;

[0217] The acquisition module 800 is further used to acquire a disturbance variable corresponding to the vehicle, wherein the disturbance variable is used to represent an environmental variable that generates a state disturbance to the driving state of the vehicle;

[0218] The construction module 801 is used to construct a target prediction model corresponding to the vehicle based on the state variable, the control variable, the output variable and the disturbance variable;

[0219] The construction module 801 is used to construct a vehicle parameter prediction model based on the difference between the reference prediction model and the target prediction model, and the vehicle parameter prediction model is used to predict the force of the vehicle suspension when the vehicle undergoes a displacement change.

[0220] In an optional embodiment, if Fig. 9 As shown, the device also includes:

[0221] A determination module 802, configured to determine a nominal equation corresponding to the vehicle based on the state variable, the control variable, and the output variable, wherein the nominal equation is used to represent a corresponding relationship between the state variable, the control variable, and the output variable;

[0222] A linearization processing module 803 is used to perform linearization processing on the nominal equation to obtain a linear nominal equation;

[0223] The determination module 802 is further used to determine the objective function corresponding to the control variable and the output variable;

[0224] The determination module 802 is further used to determine the minimum value corresponding to the control variable in the objective function;

[0225] The determination module 802 is further configured to adjust the initial prediction model based on the minimum value and the linear nominal equation to obtain the benchmark prediction model.

[0226] In an optional embodiment, if Fig. 9 As shown, the device also includes:

[0227] A discretization processing module 804 is used to perform discretization processing on the linear nominal equation to obtain a discrete state equation;

[0228] A prediction module 805 is used to perform a rolling prediction process on the discrete state equation to obtain a rolling state equation;

[0229] The determination module 802 is further configured to adjust the initial prediction model based on the minimum value and the rolling state equation to obtain the reference prediction model.

[0230] In an optional embodiment, if Fig. 9 As shown, the determination module 802 is further used to determine the ideal path displacement corresponding to the vehicle based on the initial state model;

[0231] The determination module 802 is further configured to determine the objective function based on the ideal path displacement and the control variable.

[0232] In an optional embodiment, if Fig. 9 As shown, the determination module 802 is further used to determine the constraint condition corresponding to the front wheel turning angle, and the constraint condition is used to indicate the value range corresponding to the front wheel turning angle;

[0233] The determination module 802 is further configured to determine the minimum value corresponding to the control variable in the objective function based on the constraint condition by using a preset solution method.

[0234] In an optional embodiment, if Fig. 9 As shown, the acquisition module 800 is also used to obtain the nominal equation corresponding to the vehicle and the disturbance variable;

[0235] The determination module 802 is further configured to adjust the nominal equation based on the disturbance variable to obtain an actual state equation;

[0236] The determination module 802 is further configured to determine an error state equation based on the nominal equation and the actual state equation;

[0237] The determination module 802 is further configured to determine the vehicle parameter prediction model based on the error state equation.

[0238] In an optional embodiment, if Fig. 9 As shown, the determination module 802 is also used to determine the error prediction model corresponding to the error state equation;

[0239] The coupling module 806 is used to couple the error prediction model and the reference prediction model to obtain the vehicle parameter prediction model.

[0240] In an optional embodiment, if Fig. 9 The determination module 802 is further used to solve the minimum value corresponding to each output variable in the error nominal state system using a preset algorithm;

[0241] The determination module 802 is further configured to train the error prediction model based on the minimum value to obtain a target error prediction model;

[0242] The coupling module 806 is further used to couple the target error prediction model and the reference prediction model to obtain the vehicle parameter prediction model.

[0243] In an embodiment of the present application, the steering system, suspension system and tire model corresponding to the vehicle are coupled to form a dynamic model, and the variables corresponding to the front wheel angle and the path displacement in the lateral direction are introduced into the steering system to construct a reference prediction model corresponding to the vehicle. Then, the road surface excitation conditions of the vehicle during actual driving are simulated to generate disturbance variables. A target prediction model is generated based on the disturbance variables and the three variables (state variables, output variables and control variables) corresponding to the dynamic model. Then, based on the difference between the target prediction model and the reference prediction model, a vehicle parameter prediction model is constructed. In actual application, the vehicle parameter prediction model is built into the intelligent driving system in the vehicle. During the driving process of the vehicle, the corresponding suspension actuating force when the vehicle displacement changes is predicted based on information such as the vehicle speed, and the corresponding suspension is called to apply the corresponding actuating force. Further improve the operational stability of the vehicle.

[0244] Fig.10 The block diagram of the structure of a computer device 1000 provided by an exemplary embodiment of the present application is shown. The computer device 1000 may be a portable mobile terminal, such as a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer or a desktop computer. The computer device 1000 may also be called a user device, a portable terminal, a laptop terminal, a desktop terminal or other names. Optionally, the computer device 800 may also be implemented as a movable device, such as a movable intelligent terminal such as a vehicle-mounted terminal.

[0245] Typically, the computer device 1000 includes a processor 1001 and a memory 1002 .

[0246] The processor 1001 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 801 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1001 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1001 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 801 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0247] The memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1002 is used to store at least one instruction, which is used to be executed by the processor 1001 to implement the model training method or behavior coding method provided in the method embodiment of the present application.

[0248] In some embodiments, the computer device 1000 may further optionally include: a peripheral device interface 1003 and at least one peripheral device. The processor 1001, the memory 1002 and the peripheral device interface 1003 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 1003 via a bus, a signal line or a circuit board. For example, the peripheral device may include: at least one of a radio frequency circuit 1004, a display screen 1005, a camera assembly 1006, an audio circuit 1007, a positioning assembly 1015 and a power supply 1008.

[0249] The peripheral device interface 1003 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 1001 and the memory 1002. In some embodiments, the processor 1001, the memory 1002, and the peripheral device interface 1003 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1001, the memory 1002, and the peripheral device interface 1003 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0250] The radio frequency circuit 1004 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1004 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 1004 converts the electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 1004 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The radio frequency circuit 1004 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1004 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0251] The display screen 1005 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1005 is a touch display screen, the display screen 1005 also has the ability to collect touch signals on the surface or above the surface of the display screen 1005. The touch signal can be input to the processor 1001 as a control signal for processing. At this time, the display screen 1005 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 1005 can be one, arranged on the front panel of the computer device 1000; in other embodiments, the display screen 1005 can be at least two, respectively arranged on different surfaces of the computer device 1000 or in a folding design; in other embodiments, the display screen 1005 can be a flexible display screen, arranged on a curved surface or a folding surface of the computer device 1000. Even, the display screen 1005 can also be arranged as a non-rectangular irregular figure, that is, a special-shaped screen. The display screen 1005 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0252] The camera assembly 1006 is used to capture images or videos. Optionally, the camera assembly 1006 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize the panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1006 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0253] The audio circuit 1007 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 1001 for processing, or input them into the radio frequency circuit 1004 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the computer device 1000. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 1001 or the radio frequency circuit 1004 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 1007 may also include a headphone jack.

[0254] The positioning component 1015 is used to locate the current geographical location of the computing device 1000 to implement navigation or LBS (Location Based Service). The positioning component 1015 can be a positioning component based on the US GPS (Global Positioning System) or China's Beidou system.

[0255] The power supply 1008 is used to power various components in the computer device 1000. The power supply 1008 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 1008 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged through a wired line, and a wireless rechargeable battery is a battery that is charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0256] In some embodiments, the computer device 1000 further includes one or more sensors 1009 . The one or more sensors 809 include, but are not limited to: an acceleration sensor 1010 , a gyroscope sensor 1011 , a pressure sensor 1012 , an optical sensor 1013 , and a proximity sensor 1014 .

[0257] The acceleration sensor 1010 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the computer device 1000. For example, the acceleration sensor 1010 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 1001 can control the display screen 1005 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 1010. The acceleration sensor 1000 can also be used to collect game or user motion data.

[0258] The gyro sensor 1011 can detect the body direction and rotation angle of the computer device 1000, and the gyro sensor 1011 can cooperate with the acceleration sensor 1010 to collect the user's 3D actions on the computer device 1000. The processor 1001 can implement the following functions based on the data collected by the gyro sensor 1011: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0259] The pressure sensor 1012 can be set on the side frame of the computer device 1000 and / or the lower layer of the display screen 1005. When the pressure sensor 1012 is set on the side frame of the computer device 1000, it can detect the user's grip signal of the computer device 1000, and the processor 1001 performs left and right hand recognition or shortcut operations according to the grip signal collected by the pressure sensor 1012. When the pressure sensor 1012 is set on the lower layer of the display screen 1005, the processor 1001 controls the operability controls on the UI interface according to the user's pressure operation on the display screen 1005. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0260] The optical sensor 1013 is used to collect the ambient light intensity. In one embodiment, the processor 1001 can control the display brightness of the display screen 1005 according to the ambient light intensity collected by the optical sensor 1013. For example, when the ambient light intensity is high, the display brightness of the display screen 1005 is increased; when the ambient light intensity is low, the display brightness of the display screen 1005 is reduced. In another embodiment, the processor 1001 can also dynamically adjust the shooting parameters of the camera assembly 1006 according to the ambient light intensity collected by the optical sensor 1013.

[0261] The proximity sensor 814, also called a distance sensor, is usually disposed on the front panel of the computer device 1000. The proximity sensor 1014 is used to collect the distance between the user and the front of the computer device 1000. In one embodiment, when the proximity sensor 1014 detects that the distance between the user and the front of the computer device 1000 is gradually decreasing, the processor 1001 controls the display screen 1005 to switch from the screen-on state to the screen-off state; when the proximity sensor 1014 detects that the distance between the user and the front of the computer device 1000 is gradually increasing, the processor 1001 controls the display screen 1005 to switch from the screen-off state to the screen-on state.

[0262] Those skilled in the art will understand that Fig.10 The structure shown in the figure does not constitute a limitation on the computer device 1000, and the computer device 1000 may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.

[0263] Fig.11 is a structural block diagram of a payment platform provided by an exemplary embodiment of the present application. Fig.11 1 is a schematic diagram of a server structure according to an exemplary embodiment. The server 1300 includes a central processing unit (CPU) 1301, a system memory 1304 including a random access memory (RAM) 1302 and a read-only memory (ROM) 1303, and a system bus 1305 connecting the system memory 1304 and the central processing unit 1301. The payment platform 1300 also includes a basic input / output system (I / O system) 1306 that helps transmit information between various devices in the payment platform, and a large-capacity storage device 1307 for storing an operating system 1313, an application program 1314 and other program modules 1315.

[0264] The basic input / output system 1306 includes a display 1308 for displaying information and an input device 1309 such as a mouse and a keyboard for user inputting information. The display 1308 and the input device 1309 are connected to the central processing unit 1301 through an input / output controller 1310 connected to the system bus 1305. The basic input / output system 1306 may also include an input / output controller 1310 for receiving and processing inputs from a plurality of other devices such as a keyboard, a mouse, or an electronic stylus. Similarly, the input / output controller 1310 also provides output to a display screen, a printer, or other types of output devices.

[0265] The mass storage device 1307 is connected to the central processing unit 1301 via a mass storage controller (not shown) connected to the system bus 1305. The mass storage device 1307 and its associated server-readable medium provide non-volatile storage for the payment platform 1300. That is, the mass storage device 1307 may include a server-readable medium (not shown) such as a hard disk or a Compact Disc Read-Only Memory (CD-ROM) drive.

[0266] Without loss of generality, the computer device readable medium may include computer device storage media and communication media. Computer device storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer device readable instructions, data structures, program modules or other data. Computer device storage media include RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), CD-ROM, Digital Video Disc (DVD) or other optical storage, cassette, tape, disk storage or other magnetic storage devices. Of course, those skilled in the art will know that the computer device storage medium is not limited to the above. The above-mentioned system memory 1304 and mass storage device 1307 can be collectively referred to as memory.

[0267] According to various embodiments of the present disclosure, the payment platform 1300 can also be connected to a remote computer device on a network through a network such as the Internet. That is, the payment platform 1300 can be connected to the network 1311 through a network interface unit 1312 connected to the system bus 1305, or the network interface unit 1312 can be used to connect to other types of networks or remote computer device systems (not shown).

[0268] The memory also includes one or more programs, which are stored in the memory. The central processing unit 1301 implements all or part of the steps of the above-mentioned model training method or behavior coding method by executing the one or more programs.

[0269] The present application also provides a computer-readable storage medium, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the method for identifying the operating status of a pipeline network provided in the above method embodiment.

[0270] The present application provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for identifying the operation status of a pipeline network provided in the above method embodiment.

[0271] Those of ordinary skill in the art will appreciate that all or part of the steps to implement the above-mentioned embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware to accomplish the steps. The program may be stored in a computer-readable storage medium, and the storage medium mentioned above may be a read-only memory, a disk, or an optical disk, etc. The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application. The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for predicting vehicle parameters, characterized in that: The method comprises: Acquire a dynamic model corresponding to the vehicle, the dynamic model including a steering model, a suspension model and a tire model, and the dynamic model is used to construct a dynamic relationship between the driving state and the physical characteristics of the vehicle; Based on the dynamic model, a state variable, a control variable and an output variable corresponding to the vehicle are obtained, wherein the state variable includes a first parameter related to the driving state and the physical characteristic, the control variable includes a second parameter related to the front wheel steering angle and the suspension force, and the output variable includes a yaw angle corresponding to the vehicle and a third parameter corresponding to the path displacement of the vehicle in the lateral direction; Based on the state variable, the control variable and the output variable, construct a reference prediction model corresponding to the vehicle; Acquiring a disturbance variable corresponding to the vehicle, wherein the disturbance variable is used to represent an environmental variable that generates a state disturbance on the driving state of the vehicle; Based on the state variable, the control variable, the output variable and the disturbance variable, construct a target prediction model corresponding to the vehicle; Based on the difference between the reference prediction model and the target prediction model, a vehicle parameter prediction model is constructed, wherein the vehicle parameter prediction model is used to predict the force of the vehicle suspension when the displacement of the vehicle changes.

2. The method according to claim 1, characterized in that The constructing a reference prediction model corresponding to the vehicle based on the state variable, the control variable and the output variable includes: Based on the state variable, the control variable and the output variable, determining a nominal equation corresponding to the vehicle, the nominal equation being used to represent a corresponding relationship between the state variable, the control variable and the output variable; Performing linearization processing on the nominal equation to obtain a linear nominal equation; Determine the objective function corresponding to the control variable and the output variable; Determining a minimum value corresponding to the control variable in the objective function; Based on the minimum value and the linear nominal equation, the initial prediction model is adjusted to obtain the benchmark prediction model.

3. The method according to claim 2, characterized in that The adjusting the initial prediction model based on the minimum value and the linear nominal equation to obtain the benchmark prediction model includes: Performing discretization processing on the linear nominal equation to obtain a discrete state equation; Performing a rolling prediction process on the discrete state equation to obtain a rolling state equation; Based on the minimum value and the rolling state equation, the initial prediction model is adjusted to obtain the reference prediction model.

4. The method according to claim 3, characterized in that The determining of the objective function corresponding to the control variable and the output variable includes: Determining an ideal path displacement corresponding to the vehicle based on the initial state model; The objective function is determined based on the ideal path displacement and the control variable.

5. The method according to claim 2, characterized in that: The determining the minimum value corresponding to the control variable in the optimization function includes: Determining a constraint condition corresponding to the front wheel steering angle, wherein the constraint condition is used to indicate a value range corresponding to the front wheel steering angle; Based on the constraint condition, the minimum value corresponding to the control variable in the objective function is determined using a preset solution method.

6. The method according to any one of claims 1 to 5, characterized in that: The constructing of a vehicle parameter prediction model based on the difference between the reference prediction model and the target prediction model comprises: Obtaining a nominal equation corresponding to the vehicle and the disturbance variable; Adjusting the nominal equation based on the disturbance variable to obtain an actual state equation; Determining an error state equation based on the nominal equation and the actual state equation; Based on the error state equation, the vehicle parameter prediction model is determined.

7. The method according to claim 6, characterized in that The step of determining the vehicle parameter prediction model based on the error state equation includes: Determining an error prediction model corresponding to the error state equation; The error prediction model and the reference prediction model are coupled to obtain the vehicle parameter prediction model.

8. The method according to claim 7, further characterized in that: The coupling of the error prediction model and the reference prediction model to obtain the vehicle parameter prediction model includes: Use the preset algorithm to solve the minimum value of each output variable corresponding to the error nominal state system; Training the error prediction model based on the minimum value to obtain a target error prediction model; The target error prediction model and the reference prediction model are coupled to obtain the vehicle parameter prediction model.

9. A vehicle parameter prediction device, characterized in that: The device comprises: An acquisition module, used to acquire a dynamic model corresponding to the vehicle, the dynamic model including a steering model, a suspension model and a tire model, and the dynamic model is used to construct a dynamic relationship between the driving state and the physical characteristics of the vehicle; The acquisition module is further used to acquire state variables, control variables and output variables corresponding to the vehicle based on the dynamic model, wherein the state variables include first parameters related to the driving state and the physical characteristics, the control variables include second parameters related to the front wheel steering angle and the suspension force, and the output variables include a yaw angle corresponding to the vehicle and a third parameter corresponding to the path displacement of the vehicle in the lateral direction; A construction module, used for constructing a reference prediction model corresponding to the vehicle based on the state variable, the control variable and the output variable; The acquisition module is further used to acquire a disturbance variable corresponding to the vehicle, wherein the disturbance variable is used to represent an environmental variable that generates a state disturbance to the driving state of the vehicle; The construction module is used to construct a target prediction model corresponding to the vehicle based on the state variable, the control variable, the output variable and the disturbance variable; The construction module is used to construct a vehicle parameter prediction model based on the difference between the baseline prediction model and the target prediction model, and the vehicle parameter prediction model is used to predict the force of the vehicle suspension when the vehicle undergoes a displacement change.

10. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the vehicle parameter prediction method as described in any one of claims 1 to 8.

Images